Road Accident Severity Detection using Telematics and Environmental Data from Connected Vehicles

Road safety affects everyone, not just Geotab customers. With several years of driving and environmental data collected from over 2 million connected vehicles, there is a great opportunity to leverage big data and machine learning to establish an accident detection system. On top of driving data and environmental data, it also contains machine diagnostic data which is hypothesized to have highly correlated features when it comes to accident detection. As such, the objective is to use this to detect the severity of an accident through a combination of ML approaches which fall under the umbrella of supervised, semi-supervised, and unsupervised learning. Based on our findings, both Geotab’s customers and the entire community will benefit from it as the end goal is to use this as a proactive measure for their clients and the respective city planners.

Faculty Supervisor:

Marsha Chechik

Student:

Amish Patel

Partner:

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

University of Toronto

Program: